1 / 18

Image Segmentation by Branch-and- Mincut

Image Segmentation by Branch-and- Mincut. Victor Lempitsky Andrew Blake Carsten Rother. An example. 0. 0. s. 1. 1. image from UIUC car dataset. [Hammer 64] [Greig, Porteous, Seheult 89]. p. q. . . Standard “graph cut” segmentation energy [Boykov, Jolly 01] :. F p =1, B p =0.

carolena
Télécharger la présentation

Image Segmentation by Branch-and- Mincut

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Image Segmentation by Branch-and-Mincut Victor LempitskyAndrew Blake Carsten Rother

  2. An example 0 0 s 1 1 image from UIUC car dataset [Hammer 64] [Greig, Porteous, Seheult 89] p q ... ... Standard “graph cut” segmentation energy [Boykov, Jolly 01]: Fp=1, Bp=0 Ppq t Fp=0, Bp=1 [Freedman, Zhang 05], [Ali, Farag, El-Baz 07],...

  3. A harder example image from UIUC car dataset Ppq 0 1 Optimal x min x, ω Optimal ω

  4. Energy optimization ω –global parameter (ω ∊ Ω0) Optimization options: • Choose reasonable ω, solve for x[Freedman, Zhang 05], [Pawan Kumar, Torr, Zisserman’ObjCut 05], [Ali, Farag, El-Baz 07] .... • Alternate between x and ω (EM) [Rother, Kolmogorov, Blake’ GrabCut 04], [Bray, Kohli, Torr’PoseCut 06], [Kim, Zabih 03].... • Optimize continuously [Chan, Vese 01], [Leventon, Grimson, Faugeras 00], [Cremers, Osher, Soatto 06], [Wang, Staib 98]... • Exhaustive search pairwise potentials (costs) ≥ 0 constant unary potentials (costs) ....shape priors, color distribution/intensity priors (Chan-Vese, GrabCut)...

  5. Our approach along x dimension along ω dimension • Extremely large, structured domain • Specific “graph cut” function • Low-dimensional (discretized) domain • Function of the general form Branch-and-bound Mincut Branch-and-Mincut [Gavrila, Philomin 99], [Lampert, Blaschko, Hofman 08], [Cremers, Schmidt, Barthel 08]

  6. Search tree Ω0 Ω0

  7. Bounding the energy: an example Fp=0, Bp=1 min Fp=1, Bp=0 ω1 ω2 Fp=0, Bp=0

  8. The lower bound s p q Ω t Computable with mincut!

  9. Lower bound • Monotonic increase towards leaves • Tightness at leaf nodes:

  10. Lower bound: example precomputed computed at runtime

  11. Branch-and-Bound Standard best-first branch-and-bound search: lowest lower bound B C A Small fraction of nodes is visited additional speed-up from “reusing” maxflow computations [Kohli,Torr 05]

  12. Results: shape prior 30,000,000 shapes Exhaustive search: 30,000,000 mincuts Branch-and-Mincut: 12,000 mincuts Speed-up: 2500 times (30 seconds per 312x272 image)

  13. Results: shape prior Left ventricle epicardium tracking (work in progress) Original sequence No shape prior Our segmentation Shape prior from other sequences 5,200,000 templates ≈20 seconds per frame Speed-up 1150 Data courtesy: Dr Harald Becher, Department of Cardiovascular Medicine, University of Oxford

  14. Result: shape prior Can add feature-based detector here UIUC car dataset

  15. Results: Discrete Chan-Vese functional cb c_p cf Chan-Vese functional [Chan, Vese 01]: ∊ [0;255]x[0;255]: quad-tree clustering Global minima of the discrete Chan-Vese functional: Speed-up 28-58 times

  16. Performance Sample Chan-Vese problem:

  17. Results: GrabCut • ω corresponds to color mixtures • [Rother, Kolmogorov, Blake’ GrabCut 04] uses EM-like search • Branch-and-Mincut searches over 65,536 starting points E = -618 E = -624 (speed-up 481) E = -628 E = -593 E = -584 (speed-up 141) E = -607

  18. Conclusion • ̶ good energy to integrate low-level and high-level knowledge in segmentation. • Branch-and-Mincut framework can find its global optimum efficiently in many cases • Ongoing work: Branch-and-X algorithms Branch-and-bound Mincut Dynamic Programming C++ code at http://research.microsoft.com/~victlem/

More Related